activity
20132022
most citedDSA: Decentralized Double Stochastic Averaging Gradient Algorithm

146 citations · 176 across the 17 of their papers we have counts for

collaborators
Showing eess.SPShow all

8 papers · 1 filter

eess.SP20213 cited

Stability of Neural Networks on Riemannian Manifolds

Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

Convolutional Neural Networks (CNNs) have been applied to data with underlying non-Euclidean structures and have achieved impressive successes. This brings the stability analysis o…

eess.SP2019

Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks

Mark Eisen, Alejandro Ribeiro

We consider the problem of optimally allocating resources across a set of transmitters and receivers in a wireless network. The resulting optimization problem takes the form of con…

eess.SP2019

Optimal WDM Power Allocation via Deep Learning for Radio on Free Space Optics Systems

Zhan Gao, Mark Eisen, Alejandro Ribeiro

Radio on Free Space Optics (RoFSO), as a universal platform for heterogeneous wireless services, is able to transmit multiple radio frequency signals at high rates in free space op…

eess.SP2019

Control-Aware Scheduling for Low Latency Wireless Systems with Deep Learning

Mark Eisen, Mohammad M. Rashid, Dave Cavalcanti +1

We consider the problem of scheduling transmissions over low-latency wireless communication links to control various control systems. Low-latency requirements are critical in devel…

eess.SP2019

Invariance-Preserving Localized Activation Functions for Graph Neural Networks

Luana Ruiz, Fernando Gama, Antonio G. Marques +1

Graph signals are signals with an irregular structure that can be described by a graph. Graph neural networks (GNNs) are information processing architectures tailored to these grap…

eess.SP2018

Connecting the Dots: Identifying Network Structure via Graph Signal Processing

Gonzalo Mateos, Santiago Segarra, Antonio G. Marques +1

Network topology inference is a prominent problem in Network Science. Most graph signal processing (GSP) efforts to date assume that the underlying network is known, and then analy…